{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NBUCXTIUAWPHAU3LSMOZ7VSMO7","short_pith_number":"pith:NBUCXTIU","schema_version":"1.0","canonical_sha256":"68682bcd14059e70536b931d9fd64c77f280c028ebb8af349c481afc3095649c","source":{"kind":"arxiv","id":"2505.00951","version":1},"attestation_state":"computed","paper":{"title":"Preserving Privacy and Utility in LLM-Based Product Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.IR","authors_text":"Dimitrios Andreadis, Jiang Zhang, Konstantinos Psounis, Tina Khezresmaeilzadeh","submitted_at":"2025-05-02T01:54:08Z","abstract_excerpt":"Large Language Model (LLM)-based recommendation systems leverage powerful language models to generate personalized suggestions by processing user interactions and preferences. Unlike traditional recommendation systems that rely on structured data and collaborative filtering, LLM-based models process textual and contextual information, often using cloud-based infrastructure. This raises privacy concerns, as user data is transmitted to remote servers, increasing the risk of exposure and reducing control over personal information. To address this, we propose a hybrid privacy-preserving recommenda"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.00951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-02T01:54:08Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"93a84c6275d54b07698abfc4efe80506add10b8cf82349f14913591fc88af9c9","abstract_canon_sha256":"f4a387f7c5e6ed6f05d1a5cf430efa0ad7b63d5df34000a9be61661c88ae843e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:42.383006Z","signature_b64":"6/OCRQJFCHfZoBGQDIMH2tekCeP/x2nlSB5OXxf1HAPSv18Uq90JJP9c6Uu+9OlRv7kOLOqXeIro7KVz+P7lBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68682bcd14059e70536b931d9fd64c77f280c028ebb8af349c481afc3095649c","last_reissued_at":"2026-07-05T10:57:42.382450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:42.382450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserving Privacy and Utility in LLM-Based Product Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.IR","authors_text":"Dimitrios Andreadis, Jiang Zhang, Konstantinos Psounis, Tina Khezresmaeilzadeh","submitted_at":"2025-05-02T01:54:08Z","abstract_excerpt":"Large Language Model (LLM)-based recommendation systems leverage powerful language models to generate personalized suggestions by processing user interactions and preferences. Unlike traditional recommendation systems that rely on structured data and collaborative filtering, LLM-based models process textual and contextual information, often using cloud-based infrastructure. This raises privacy concerns, as user data is transmitted to remote servers, increasing the risk of exposure and reducing control over personal information. To address this, we propose a hybrid privacy-preserving recommenda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00951","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.00951/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.00951","created_at":"2026-07-05T10:57:42.382511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00951v1","created_at":"2026-07-05T10:57:42.382511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00951","created_at":"2026-07-05T10:57:42.382511+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBUCXTIUAWPH","created_at":"2026-07-05T10:57:42.382511+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBUCXTIUAWPHAU3L","created_at":"2026-07-05T10:57:42.382511+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBUCXTIU","created_at":"2026-07-05T10:57:42.382511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7","json":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7.json","graph_json":"https://pith.science/api/pith-number/NBUCXTIUAWPHAU3LSMOZ7VSMO7/graph.json","events_json":"https://pith.science/api/pith-number/NBUCXTIUAWPHAU3LSMOZ7VSMO7/events.json","paper":"https://pith.science/paper/NBUCXTIU"},"agent_actions":{"view_html":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7","download_json":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7.json","view_paper":"https://pith.science/paper/NBUCXTIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00951&json=true","fetch_graph":"https://pith.science/api/pith-number/NBUCXTIUAWPHAU3LSMOZ7VSMO7/graph.json","fetch_events":"https://pith.science/api/pith-number/NBUCXTIUAWPHAU3LSMOZ7VSMO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7/action/storage_attestation","attest_author":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7/action/author_attestation","sign_citation":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7/action/citation_signature","submit_replication":"https://pith.science/pith/NBUCXTIUAWPHAU3LSMOZ7VSMO7/action/replication_record"}},"created_at":"2026-07-05T10:57:42.382511+00:00","updated_at":"2026-07-05T10:57:42.382511+00:00"}